如何調用向量化滑動窗口的切片上的函數？

Question

我試圖矢量化對象檢測的滑動窗口搜索。到目前爲止，我已經能夠使用numpy廣播將我的主圖像切片成窗口大小的切片，這些切片存儲在下面所示的變量'all_windows'中。我已經驗證了實際值匹配，所以我很滿意這一點。

下一部分是我遇到麻煩的地方。我想索引到'all_windows'數組，因爲我調用了patchCleanNPredict（）函數，以便我可以以相似的矢量化格式將每個窗口傳遞到函數中。

我試圖創建一個名爲new_indx的數組，該數組將包含2d數組中的切片索引，例如（[0,0]，[1,0]，[2,0] ...），但已經遇到問題。

我希望最終得到每個窗口的置信度值數組。下面的代碼在python 3.5中工作。預先感謝任何幫助/建議。

import numpy as np 

def patchCleanNPredict(patch): 
    # patch = cv2.resize()# shrink patches with opencv resize function 
    patch = np.resize(patch.flatten(),(1,np.shape(patch.flatten())[0])) # flatten the patch 
    print('patch: ',patch.shape) 
    # confidence = predict(patch) # fake function showing prediction intent 
    return # confidence 


window = (30,46)# window dimensions 
strideY = 10 
strideX = 10 

img = np.random.randint(0,245,(640,480)) # image that is being sliced by the windows 

indx = np.arange(0,img.shape[0]-window[1],strideY)[:,None]+np.arange(window[1]) 
vertical_windows = img[indx] 
print(vertical_windows.shape) # returns (60,46,480) 


vertical_windows = np.transpose(vertical_windows,(0,2,1)) 
indx = np.arange(0,vertical_windows.shape[1]-window[0],strideX)[:,None]+np.arange(window[0]) 
all_windows = vertical_windows[0:vertical_windows.shape[0],indx] 
all_windows = np.transpose(all_windows,(1,0,3,2)) 

print(all_windows.shape) # returns (45,60,46,30) 


data_patch_size = (int(window[0]/2),int(window[1]/2)) # size the windows will be shrunk to 

single_patch = all_windows[0,0,:,:] 
patchCleanNPredict(single_patch) # prints the flattened patch size (1,1380) 

new_indx = (1,1) # should this be an array of indices? 
patchCleanNPredict(all_windows[new_indx,:,:]) ## this is where I'm having trouble 

Answer 1

要以量化的方式我最後不得不做調整，並重新安排np.transpose得到它所有正確的播出量好評估上的所有窗口的功能。下面的代碼工作，並有循環顯示，並確認圖像窗口沒有被混淆/混淆。他們將被刪除/評論全速運行。

一個小的免責聲明：我認爲在2D矩陣中必須有滑動窗口的更清晰的實現，但是因爲我無法找到以下任何示例可能會幫助其他人。另外，一些頻繁的重新排列和調整大小可能可以通過對廣播語法更全面的理解來清除。

import numpy as np 
import cv2 


def Predict(flattened_patches): 
    # taking the mean of the flattened windows and then returning the 
    # index of the row (window) with the highest mean, a predicter would have the same syntax 
    results = flattened_patches.mean(1) 
    max_index = results.argmax() 
    return results, max_index 

## -------- image and sliding window setup ------------------------- 
AR = 1.45 # choose an aspect ratio to maintain throughout scaling steps 
win_h = 200 # window height 
win_w = int(win_h/AR) # window width 
window = (win_w,win_h)# window dimensions 
strideY = 100 
strideX = 100 

data_patch_size = (30,46) # size the windows will be shrunk to for object detection 

img = cv2.imread('picture6.png') # load an image to slide over 

cv2.namedWindow('image',cv2.WINDOW_NORMAL) 
cv2.resizeWindow("image",int(img.shape[1]/2),int(img.shape[0]/2)) # shrink the image viewing window if you have large images 

img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) 
## -------- end of, image and sliding window setup -------------------- 

## -------- sliding window vectorization steps -------------------------- 
num_vert_windows = len(np.arange(0,img.shape[0]-window[1],strideY)) # number of vertical windows that will be created 
indx = np.arange(0,img.shape[0]-window[1],strideY)[:,None]+np.arange(window[1]) # index that will be broadcasted across image 
vertical_windows = img[indx] # array of windows win_h tall and the full width of the image 

vertical_windows = np.transpose(vertical_windows,(0,2,1)) # transpose to prep for broadcasting 
num_horz_windows = len(np.arange(0,vertical_windows.shape[1]-window[0],strideX)) # number of horizontal windows that will be created 
indx = np.arange(0,vertical_windows.shape[1]-window[0],strideX)[:,None]+np.arange(window[0]) # index for broadcasting across vertical windows 
all_windows = vertical_windows[0:vertical_windows.shape[0],indx] # array of all the windows 
## -------- end of, sliding window vectorization ------------------------ 

## ------- The below code rearranges and flattens the windows into a single matrix of pixels in columns and each window 
## ------- in a row which makes evaluating a function over every window in a vectorized manner easier 

total_windows = num_vert_windows*num_horz_windows 

all_windows = np.transpose(all_windows,(3,2,1,0)) # rearrange for resizing and intuitive indexing 

print('all_windows shape as stored in 2d matrix:', all_windows.shape) 
for i in range(all_windows.shape[2]): # display windows for visual confirmation 
    for j in range(all_windows.shape[3]): 
     cv2.imshow('image',all_windows[:,:,i,j]) 
     cv2.waitKey(100) 

all_windows = np.resize(all_windows,(win_h,win_w,total_windows)) 
print('all_windows shape after folding into 1d vector:', all_windows.shape) 
for i in range(all_windows.shape[2]): # display windows for visual confirmation 
    cv2.imshow('image',all_windows[:,:,i]) 
    cv2.waitKey(100) 

# shrinking all the windows down to the size needed for object detect predictions 
small_windows = cv2.resize(all_windows[:,:,0:all_windows.shape[2]],data_patch_size,0,0,cv2.INTER_AREA) 
print('all_windows shape after shrinking to evaluation size:',small_windows.shape) 
for i in range(small_windows.shape[2]): # display windows for vis. conf. 
    cv2.imshow('image',small_windows[:,:,i]) 
    cv2.waitKey(100) 

# flattening and rearranging the window data so that the pixels are in columns and each window is a row 
flat_windows = np.resize(small_windows,(data_patch_size[0]*data_patch_size[1],total_windows)) 
flat_windows = np.transpose(flat_windows) 
print('shape of the window data to send to the predicter:',np.shape(flat_windows)) 

results, max_index = Predict(flat_windows) # get predictions on all the windows